Abstract: Systems and methods are described herein for monitoring a gameplay session for violations of a policy and creating a remediation gameplay session through which remediation can be provided to players or player accounts that violate gameplay policies. The systems and methods can create a remediation gameplay session based in part on the game state data of the gameplay session during which the violation occurs.

Abstract: In response to receiving user input command for sending a contextually aware communication, a computer system is configured to use game state data to determine a target location that a player is focusing on in a virtual environment in a video game, identify a unit that the player likely wants to communicate about based on at least priorities of unit types and proximities of units to the target location, and select a communication action for performance. Different communication actions can be performed in response to the same user input command when the game state data indicates different game states.

Abstract: Techniques are disclosed that can obtain a description of intended digital content data in a producer computer, create a task graph of the intended digital content data, send the task graph to a consumer computer over a bus, execute the task graph locally in the consumer computer to realize an approximation of the intended digital content data, and render the approximation of the intended digital content data on a local display or other appropriate output device.

Abstract: Various aspects of the subject technology relate to systems, methods, and machine-readable media for preventing rendering of a character in a video game. The method includes receiving an action regarding a first character rendered in a first-person point of view (POV), the action causing the POV of the first character to change from the first-person POV to a third-person POV. The method includes detecting the POV of the first character is to be changed. The method includes determining characters are outside of a field of view (FOV) of the first character in the first-person POV and would be within the FOV of the first character in the third-person POV. The method includes changing the POV of the first character from the first-person POV to a third person POV. The method includes causing rendering of the video game in a third-person POV of the first character, the rendering preventing rendering of other characters.

Abstract: An imitation learning system may learn how to play a video game based on user interactions by a tester or other user of the video game. The imitation learning system may develop an imitation learning model based, at least in part, on the tester's interaction with the video game and the corresponding state of the video game to determine or predict actions that may be performed when interacting with the video game. The imitation learning system may use the imitation learning model to control automated agents that can play additional instances of the video game. Further, as the user continues to interact with the video game during testing, the imitation learning model may continue to be updated. Thus, the interactions by the automated agents with the video game may, over time, almost mimic the interaction by the user enabling multiple tests of the video game to be performed simultaneously.

Abstract: This specification relates to the generation of animation data using recurrent neural networks. According to a first aspect of this specification, there is described a computer implemented method comprising: sampling an initial hidden state of a recurrent neural network (RNN) from a distribution; generating, using the RNN, a sequence of frames of animation from the initial state of the RNN and an initial set of animation data comprising a known initial frame of animation, the generating comprising, for each generated frame of animation in the sequence of frames of animation: inputting, into the RNN, a respective set of animation data comprising the previous frame of animation data in the sequence of frames of animation; generating, using the RNN and based on a current hidden state of the RNN, the frame of animation data; and updating the hidden state of the RNN based on the input respective set of animation data.

Abstract: The disclosure provides a video playback system for use within a game application and/or other interactive computing environments. The video playback system can be used to capture gameplay during execution of a game application. The captured gameplay video can be processed and stored within the game application or in a network accessible location.

Abstract: An image capture system includes: a first mobile unit configured to move around the target area; a second mobile unit adjustably coupled to the first mobile unit; a dual-camera unit, operatively coupled to the second mobile unit, including: a first camera to capture structural data; and a second camera to capture color data, wherein the first mobile unit and the second mobile unit are configured to move the first camera and the second camera.

Abstract: The present disclosure provides a system for automating graphical testing during video game development. The system can use Deep Convolutional Neural Networks (DCNNs) to create a model to detect graphical glitches in video games. The system can use an image, a video game frame, as input to be classified into one of defined number of classifications. The classifications can include a normal image and one of a plurality of different kinds of glitches. In some embodiments, the glitches can include corrupted textures, including low resolution textures and stretched textures, missing textures, and placeholder textures. The system can apply a confidence measure to the analysis to help reduce the number of false positives.

Abstract: A visual-programming tool accesses a datastore of existing program data, which includes program code associated with a plurality of programs, (e.g., games), stored as multi-layer trees of nodes with logical connections signifying relationships between nodes of adjacent layers. The tool uses machine learning to determine multi-layer trees of predictions including at least one chain of nodes from the multi-layer tree of nodes. The tool provides one or more of the multi-layer trees of predictions including chains of nodes for presentation via a graphical-user interface and receives a gliding gesture input indicating a decision between nodes of the one or more layers. The input indicates a decision associated with selecting a chain of nodes when the input traverses more than one layer. The visual-programming tool provides further layers from the one or more multi-layer trees of predictions based on the received input without requiring acceptance of individual nodes at each layer.

Abstract: Some embodiments herein disclose intelligent priority evaluators configured to perform a method that prioritizes tasks submitted by various users, even if the tasks are similarly classified. The scheduling system can collect, calculate, and use various criteria to determine a reward score in order to prioritize one task over another, such as for dynamic scheduling purposes. This can be performed in addition to or as a replacement for receiving user designations of priority.

Abstract: Various aspects of the subject technology relate to systems, methods, and machine-readable media for authenticating user accounts. The method includes authenticating at least one user account of a plurality of user accounts for lobbying into a session. The method includes generating at least one authenticated socket in a server for each authenticated user account. The method includes adding the at least one user account to the at least one authenticated socket. The method includes adding non-authenticated user accounts to non-authenticated sockets of a plurality of non-authenticated sockets. The method includes detecting network traffic flowing into the plurality of authenticated sockets and the plurality of non-authenticated sockets. The method includes disconnecting non-authenticated user accounts from the server when a threshold amount of suspicious and/or malicious network traffic is detected in a non-authenticated socket.

Abstract: A high-skilled-low-level detection system may detect high-skilled entities in low-level matches of an online gaming. The system may identify a plurality of entities that are within a first category of entities eligible to be matched by a matchmaking algorithm. The system may then determine respective feature sets based at least in part on gameplay data associated with the plurality of entities and perform anomaly detection on the respective feature sets. The system may then determine, based on the anomaly detection, an anomalous entity of the plurality of entities and cause the matchmaking algorithm to match the anomalous entity with other entities that are in a second category of entities.

Abstract: A method comprises determining positions of render strands based on a simulation model of simulation strands. Each simulation strand corresponds to a render strand. For a first range of values of a metric up to a threshold value, the simulation model is determined in a first simulation level using a first set of simulation strands. For a second range of values of the metric from a second threshold value, the simulation model is determined in a second simulation level using a subset of the first set of simulation strands. For metric values between the first and second threshold values, a transition between first and second simulation levels comprises computing the simulation model in the first level of detail. Positions of the render strands during the transition are derived from the first set of simulation strands having a first weight, and the second set of simulation strands having a second weight.

Abstract: A system for use in video game development to generate expressive speech audio comprises a user interface configured to receive user-input text data and a user selection of a speech style. The system includes a machine-learned synthesizer comprising a text encoder, a speech style encoder and a decoder. The machine-learned synthesizer is configured to generate one or more text encodings derived from the user-input text data, using the text encoder of the machine-learned synthesizer; generate a speech style encoding by processing a set of speech style features associated with the selected speech style using the speech style encoder of the machine-learned synthesizer; combine the one or more text encodings and the speech style encoding to generate one or more combined encodings; and decode the one or more combined encodings with the decoder of the machine-learned synthesizer to generate predicted acoustic features.

Abstract: A computing system may provide functionality for controlling an animated model to perform actions and to perform transitions therebetween. The system may determine, from among a plurality of edges from a first node of a control graph to respective other nodes of the control graph, a selected edge from the first control node to a selected node. The system may then determine controls for an animated model in a simulation based at least in part on the selected edge, control data associated with the selected node, a current simulation state of the simulation, and a machine learned algorithm, determine an updated simulation state of the simulation based at least in part on the controls for the animated model, and adapt one or more parameters of the machine learned algorithm based at least in part on the updated simulation state and a desired simulation state.

Abstract: A spectator system may provide for spectating in online gaming. The spectator system may receive, at a spectator server, game state data from a game simulation server hosting an online game for one or more players, generate one or more spectator game state data corresponding to one or more spectator devices and output the one or more spectator game state data to the spectator devices. The spectator server may further output the game state data to another spectator server.

Abstract: The present disclosure provides for the dynamic mapping of functions within a content development application to a control surface including a plurality of distinct modular input consoles. The system includes a console controller that is configured to monitor usage of the content development application by the user and to dynamically control the mapping of functions to the control surface based on the contextual operation of the content development application. The console controller can determine the functions that are to be mapped to the control surface based on the context of the application and the functions that are prioritized for use by a user of the content development application.

Abstract: A bot detection system and method analyzes application programming interface (API) data associated with an online gaming player account to make a determination of whether the player account is engaging in cheating by using a bot during online game play. The API data may be analyzed to generate API metadata that is descriptive of the API data, such as an indication of how many API calls were made to a particular API during a particular time period on behalf of the player account. The API data may be applied to one or more bot detection models to make an assessment of whether the player account is using a bot. If bot usage is detected with a player account, enforcement actions, such as slowing down game play or banning the player account, may be implemented for that player account.

Abstract: A method, device, and computer-readable storage medium for generating a simplified mesh. The method includes: receiving an input mesh that is a polygonal mesh; identifying one or more submeshes of the input mesh; fitting a set of shapes to the one or more submeshes to determine which shapes approximate which submeshes within a threshold value; for each submesh that is associated with at least one shape that approximates the submesh within the threshold value, generating a set of proxy levels-of-detail (LODs) for the submesh, wherein each proxy LOD is a polygonal mesh corresponding to the shape that approximates the submesh; generating for each submesh, a set of traditionally simplified levels-of-detail (LODs) based on simplifying the submesh; and generating the simplified mesh based on selecting one proxy LOD or one traditionally simplified LOD for each submesh of the one or more submeshes.